Plan a page's information architecture from a brief

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the fixed 10-14 section count, the deliberate omission of components and the reasoning, the inclusion of a motion system and tokens, and the critical constraint that the reference biases but never derives motion. It also explains the downstream workflow. This is thorough and non-contradictory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loaded with the primary output and then provides necessary exclusions, reasoning, and parameter caveats. Every sentence carries information, and the density is justified by the tool's complexity. A slightly tighter structure could group the reference behavior, but it remains readable and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and annotations, the description does an excellent job of conveying what the tool returns (sections with roles, content needs, motion system), what it intentionally omits (components), and how to proceed afterward. It also covers the optional reference's role. This is complete enough for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, and the description adds substantial meaning to the `reference` parameter (static art direction, biasing motion, not deriving motion), which the schema only lists as an object without explaining its effect. The `brief` and `archetype` are partially covered by schema and enum; the description adds no new detail for archetype but doesn't need to. Overall, it compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource pairing ('Returns the SECTIONS a page of this kind needs') and clearly distinguishes this planning action from component lookups by explicitly stating it returns NO components. It also names the companion tool (suggest_mechanics) and clarifies the motion system output, making the tool's purpose unmistakable among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit sequencing guidance: 'Ask for mechanics afterwards, one section at a time, with suggest_mechanics.' It also tells the agent when NOT to use this tool (for component selection) by explaining that components are deliberately excluded, and when to rely on this tool instead of search (for catalog-uncovered roles). This is clear usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.